This is an Datasets Notebook. When you execute code within the notebook, the results appear beneath the code.

• First, let’s import the dataset that we selected:

d <- read.csv("/Users/khaled/Desktop/Programming/Teaching/Datasets/scrubbed.csv", na.strings = "", stringsAsFactors = F) %>% filter(country == "us")

d %>% count(state, sort = T)

d %>% count(shape, sort = T) 

d %>% separate(datetime, c("Date", "Time"), sep = " ") -> d
d %>% count(Date, sort = T)

d %>% mutate(Date = mdy(Date)) %>% mutate_at(vars(Date), funs(year, month, day)) -> d

## Warning: funs() is soft deprecated as of dplyr 0.8.0
## please use list() instead
## 
##   # Before:
##   funs(name = f(.))
## 
##   # After: 
##   list(name = ~ f(.))
## This warning is displayed once per session.

d %>% mutate(
    season = case_when(
      month %in% 9:11 ~ "Fall",
      month %in% c(12,1,2)  ~ "Winter",
      month %in%  3:5  ~ "Spring",
      TRUE ~ "Summer")) -> d

d %>% count(year, sort = T) %>% ggplot(aes(year, n)) + geom_col()

d %>% group_by(month) %>% mutate(n = n()) %>% select(month, n , season) %>% distinct() %>% 
  ggplot(aes(month, n)) + geom_col(aes(fill = season)) + scale_x_continuous(breaks = 1:12) +
  coord_cartesian(ylim=c(3000,8000)) + geom_smooth(se = F)

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

d %>% ggplot(aes(day)) + geom_density() + facet_wrap(~month)

d %>% count(month) %>% ggplot(aes(month, n)) + geom_point() + geom_smooth() +
  scale_x_continuous(breaks = 1:12)

## `geom_smooth()` using method = 'loess' and formula 'y ~ x'

d %>% count(month, sort = T)

d %>% mutate_at(vars(latitude, duration..seconds.), as.numeric) -> d

## Warning: NAs introduced by coercion

# d %>% filter(year == 2012) %>% count(Date) %>% filter(Date == "2012-07-04") -> nn
d %>% filter(year == 2012) %>% group_by(Date) %>% mutate(n = n()) %>% 
  select(year, Date , n) %>% distinct() -> d2
d2 %>% ggplot(aes(Date, n)) + geom_line() +
  ggrepel::geom_label_repel(data = subset(d2,n > 50) , aes(label = as.character(Date)), color = "red", segment.color = "red") +
  facet_wrap(~year, scales = "free")

d  %>% filter(!state %in% c("ak", "hi", "pr")) %>%
  ggplot(aes(longitude, latitude)) +
  geom_point(alpha = 0.1) +
  coord_map() + borders("state") + theme_void() +
  labs(title = 'Year: {round(frame_time)}') +
  gganimate::transition_time(year)

## 
## Attaching package: 'maps'

## The following object is masked from 'package:purrr':
## 
##     map